Papers › An Empirical Study of Scaling Law for OCR

An Empirical Study of Scaling Law for OCR

29 Dec 2023arXiv:2401.00028archive 2025-07-28

Miao Rang, Zhenni Bi, Chuanjian Liu, Yunhe Wang, Kai Han

The laws of model size, data volume, computation and model performance have been extensively studied in the field of Natural Language Processing (NLP). However, the scaling laws in Optical Character Recognition (OCR) have not yet been investigated. To address this, we conducted comprehensive studies that involved examining the correlation between performance and the scale of models, data volume and computation in the field of text recognition.Conclusively, the study demonstrates smooth power laws between performance and model size, as well as training data volume, when other influencing factors are held constant. Additionally, we have constructed a large-scale dataset called REBU-Syn, which comprises 6 million real samples and 18 million synthetic samples. Based on our scaling law and new dataset, we have successfully trained a scene text recognition model, achieving a new state-ofthe-art on 6 common test benchmarks with a top-1 average accuracy of 97.42%. The models and dataset are publicly available at https://github.com/large-ocr-model/large-ocr-model.github.io.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

large-ocr-model/large-ocr-model.github.io officialmentioned in papermentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Optical Character RecognitionOptical Character Recognition (OCR)Scene Text Recognition

Datasets

Introduced by this paper, per the archive.

REBU-Syn

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Scene Text Recognition CUTE80 CLIP4STR-B* Accuracy 99.65 #3 of 18 Archive leaderboard report
Scene Text Recognition ICDAR2013 CLIP4STR-L* Accuracy 99.42 #1 of 38 Archive leaderboard report
Scene Text Recognition ICDAR2015 CLIP4STR-L* Accuracy 92.6 #2 of 27 Archive leaderboard report
Scene Text Recognition SVT CLIP4STR-B* Accuracy 98.76 #3 of 37 Archive leaderboard report
Scene Text Recognition SVTP CLIP4STR-L* Accuracy 98.13 #3 of 17 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections